Showing 1–50 of 130 results for author: Cao, N

Figures as Interfaces: Toward LLM-Native Artifacts for Scientific Discovery

Authors: Yifang Wang, Rui Sheng, Erzhuo Shao, Yifan Qian, Haotian Li, Nan Cao, Dashun Wang

Abstract: Large language models (LLMs) are transforming scientific workflows, not only through their generative capabilities but also through their emerging ability to use tools, reason about data, and coordinate complex analytical tasks. Yet in most human-AI collaborations, the primary outputs, figures, are still treated as static visual summaries: once rendered, they are handled by both humans and multimo… ▽ More Large language models (LLMs) are transforming scientific workflows, not only through their generative capabilities but also through their emerging ability to use tools, reason about data, and coordinate complex analytical tasks. Yet in most human-AI collaborations, the primary outputs, figures, are still treated as static visual summaries: once rendered, they are handled by both humans and multimodal LLMs as images to be re-interpreted from pixels or captions. The emergent capabilities of LLMs open an opportunity to fundamentally rethink this paradigm. In this paper, we introduce the concept of LLM-native figures: data-driven artifacts that are simultaneously human-legible and machine-addressable. Unlike traditional plots, each artifact embeds complete provenance: the data subset, analytical operations and code, and visualization specification used to generate it. As a result, an LLM can "see through" the figure--tracing selections back to their sources, generating code to extend analyses, and orchestrating new visualizations through natural-language instructions or direct manipulation. We implement this concept through a hybrid language-visual interface that integrates LLM agents with a bidirectional mapping between figures and underlying data. Using the science of science domain as a testbed, we demonstrate that LLM-native figures can accelerate discovery, improve reproducibility, and make reasoning transparent across agents and users. More broadly, this work establishes a general framework for embedding provenance, interactivity, and explainability into the artifacts of modern research, redefining the figure not as an end product, but as an interface for discovery. For more details, please refer to the demo video available at www.llm-native-figure.com. △ Less

Submitted 9 April, 2026; originally announced April 2026.

Probabilistic Tree Inference Enabled by FDSOI Ferroelectric FETs

Authors: Pengyu Ren, Xingtian Wang, Boyang Cheng, Jiahui Duan, Giuk Kim, Xuezhong Niu, Halid Mulaosmanovic, Stefan Duenkel, Sven Beyer, X. Sharon Hu, Ningyuan Cao, Kai Ni

Abstract: Artificial intelligence applications in autonomous driving, medical diagnostics, and financial systems increasingly demand machine learning models that can provide robust uncertainty quantification, interpretability, and noise resilience. Bayesian decision trees (BDTs) are attractive for these tasks because they combine probabilistic reasoning, interpretable decision-making, and robustness to nois… ▽ More Artificial intelligence applications in autonomous driving, medical diagnostics, and financial systems increasingly demand machine learning models that can provide robust uncertainty quantification, interpretability, and noise resilience. Bayesian decision trees (BDTs) are attractive for these tasks because they combine probabilistic reasoning, interpretable decision-making, and robustness to noise. However, existing hardware implementations of BDTs based on CPUs and GPUs are limited by memory bottlenecks and irregular processing patterns, while multi-platform solutions exploiting analog content-addressable memory (ACAM) and Gaussian random number generators (GRNGs) introduce integration complexity and energy overheads. Here we report a monolithic FDSOI-FeFET hardware platform that natively supports both ACAM and GRNG functionalities. The ferroelectric polarization of FeFETs enables compact, energy-efficient multi-bit storage for ACAM, and band-to-band tunneling in the gate-to-drain overlap region and subsequent hole storage in the floating body provides a high-quality entropy source for GRNG. System-level evaluations demonstrate that the proposed architecture provides robust uncertainty estimation, interpretability, and noise tolerance with high energy efficiency. Under both dataset noise and device variations, it achieves over 40% higher classification accuracy on MNIST compared to conventional decision trees. Moreover, it delivers more than two orders of magnitude speedup over CPU and GPU baselines and over four orders of magnitude improvement in energy efficiency, making it a scalable solution for deploying BDTs in resource-constrained and safety-critical environments. △ Less

Submitted 6 April, 2026; originally announced April 2026.

A Unified Memory Perspective for Probabilistic Trustworthy AI

Authors: Xueji Zhao, Likai Pei, Jianbo Liu, Kai Ni, Ningyuan Cao

Abstract: Trustworthy artificial intelligence increasingly relies on probabilistic computation to achieve robustness, interpretability, security and privacy. In practical systems, such workloads interleave deterministic data access with repeated stochastic sampling across models, data paths and system functions, shifting performance bottlenecks from arithmetic units to memory systems that must deliver both… ▽ More Trustworthy artificial intelligence increasingly relies on probabilistic computation to achieve robustness, interpretability, security and privacy. In practical systems, such workloads interleave deterministic data access with repeated stochastic sampling across models, data paths and system functions, shifting performance bottlenecks from arithmetic units to memory systems that must deliver both data and randomness. Here we present a unified data-access perspective in which deterministic access is treated as a limiting case of stochastic sampling, enabling both modes to be analyzed within a common framework. This view reveals that increasing stochastic demand reduces effective data-access efficiency and can drive systems into entropy-limited operation. Based on this insight, we define memory-level evaluation criteria, including unified operation, distribution programmability, efficiency, robustness to hardware non-idealities and parallel compatibility. Using these criteria, we analyze limitations of conventional architectures and examine emerging probabilistic compute-in-memory approaches that integrate sampling with memory access, outlining pathways toward scalable hardware for trustworthy AI. △ Less

Submitted 26 March, 2026; originally announced March 2026.

Bounding the Fragmentation of B-Trees Subject to Batched Insertions

Authors: Michael A. Bender, Aaron Bernstein, Nairen Cao, Alex Conway, Martín Farach-Colton, Hanna Komlós, Yarin Shechter, Nicole Wein

Abstract: The issue of internal fragmentation in data structures is a fundamental challenge in database design. A seminal result of Yao in this field shows that evenly splitting the leaves of a B-tree against a workload of uniformly random insertions achieves space utilization of around 69%. However, many database applications perform batched insertions, where a small run of consecutive keys is inserted at… ▽ More The issue of internal fragmentation in data structures is a fundamental challenge in database design. A seminal result of Yao in this field shows that evenly splitting the leaves of a B-tree against a workload of uniformly random insertions achieves space utilization of around 69%. However, many database applications perform batched insertions, where a small run of consecutive keys is inserted at a single position. We develop a generalization of Yao's analysis to provide rigorous treatment of such batched workloads. Our approach revisits and reformulates the analytical structure underlying Yao's result in a way that enables generalization and is used to argue that even splitting works well for many workloads in our extended class. For the remaining workloads, we develop simple alternative strategies that provably maintain good space utilization. △ Less

Submitted 12 March, 2026; originally announced March 2026.

Comments: To appear at PODS 2026, 30 pages, 5 figures

CogBlender: Towards Continuous Cognitive Intervention in Text-to-Image Generation

Authors: Shengqi Dang, Jiaying Lei, Yi He, Ziqing Qian, Nan Cao

Abstract: Beyond conveying semantic information, an image can also manifest cognitive attributes that elicit specific cognitive processes from the viewer, such as memory encoding or emotional response. While modern text-to-image models excel at generating semantically coherent content, they remain limited in their ability to control such cognitive properties of images (e.g., valence, memorability), often fa… ▽ More Beyond conveying semantic information, an image can also manifest cognitive attributes that elicit specific cognitive processes from the viewer, such as memory encoding or emotional response. While modern text-to-image models excel at generating semantically coherent content, they remain limited in their ability to control such cognitive properties of images (e.g., valence, memorability), often failing to align with the specific psychological intent. To bridge this gap, we introduce CogBlender, a framework that enables continuous and multi-dimensional intervention of cognitive properties during text-to-image generation. Our approach is built upon a mapping between the Cognitive Space, representing the space of cognitive properties, and the Semantic Manifold, representing the manifold of the visual semantics. We define a set of Cognitive Anchors, serving as the boundary points for the cognitive space. Then we reformulate the velocity field within the flow-matching process by interpolating from the velocity field of different anchors. Consequently, the generative process is driven by the velocity field and dynamically steered by multi-dimensional cognitive scores, enabling precise, fine-grained, and continuous intervention. We validate the effectiveness of CogBlender across four representative cognitive dimensions: valence, arousal, dominance, and image memorability. Extensive experiments demonstrate that our method achieves effective cognitive intervention. Our work provides an effective paradigm for cognition-driven creative design. △ Less

Submitted 10 March, 2026; originally announced March 2026.

Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic

Authors: Shuai Liu, Ning Cao, Yile Chen, Yue Jiang, Gao Cong

Abstract: Mobility trajectory data provide essential support for smart city applications. However, such data are often difficult to obtain. Meanwhile, most existing trajectory generation methods implicitly assume that at least a subset of real mobility data from target city is available, which limits their applicability in data-inaccessible scenarios. In this work, we propose a new problem setting, called b… ▽ More Mobility trajectory data provide essential support for smart city applications. However, such data are often difficult to obtain. Meanwhile, most existing trajectory generation methods implicitly assume that at least a subset of real mobility data from target city is available, which limits their applicability in data-inaccessible scenarios. In this work, we propose a new problem setting, called bus-conditioned zero-shot trajectory generation, where no mobility trajectories from a target city are accessible. The generation process relies solely on source city mobility data and publicly available bus timetables from both cities. Under this setting, we propose MobTA, the first approach to introduce task arithmetic into trajectory generation. MobTA models the parameter shift from bus-timetable-based trajectory generation to mobility trajectory generation in source city, and applies this shift to target city through arithmetic operations on task vectors. This enables trajectory generation that reflects target-city mobility patterns without requiring any real mobility data from it. Furthermore, we theoretically analyze MobTA's stability across base and instruction-tuned LLMs. Extensive experiments show that MobTA significantly outperforms existing methods, and achieves performance close to models finetuned using target city mobility trajectories. △ Less

Submitted 13 February, 2026; originally announced February 2026.

Beyond Input-Output: Rethinking Creativity through Design-by-Analogy in Human-AI Collaboration

Authors: Xuechen Li, Shuai Zhang, Nan Cao, Qing Chen

Abstract: While the proliferation of foundation models has significantly boosted individual productivity, it also introduces a potential challenge: the homogenization of creative content. In response, we revisit Design-by-Analogy (DbA), a cognitively grounded approach that fosters novel solutions by mapping inspiration across domains. However, prevailing perspectives often restrict DbA to early ideation or… ▽ More While the proliferation of foundation models has significantly boosted individual productivity, it also introduces a potential challenge: the homogenization of creative content. In response, we revisit Design-by-Analogy (DbA), a cognitively grounded approach that fosters novel solutions by mapping inspiration across domains. However, prevailing perspectives often restrict DbA to early ideation or specific data modalities, while reducing AI-driven design to simplified input-output pipelines. Such conceptual limitations inadvertently foster widespread design fixation. To address this, we expand the understanding of DbA by embedding it into the entire creative process, thereby demonstrating its capacity to mitigate such fixation. Through a systematic review of 85 studies, we identify six forms of representation and classify techniques across seven stages of the creative process. We further discuss three major application domains: creative industries, intelligent manufacturing, and education and services, demonstrating DbA's practical relevance. Building on this synthesis, we frame DbA as a mediating technology for human-AI collaboration and outline the potential opportunities and inherent risks for advancing creativity support in HCI and design research. △ Less

Submitted 10 February, 2026; originally announced February 2026.

Comments: 20 pages, 9 figures. Accepted to the 2026 CHI Conference on Human Factors in Computing Systems

ACM Class: H.5.m

Journal ref: Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26)

When and Where to Attack? Stage-wise Attention-Guided Adversarial Attack on Large Vision Language Models

Authors: Jaehyun Kwak, Nam Cao, Boryeong Cho, Segyu Lee, Sumyeong Ahn, Se-Young Yun

Abstract: Adversarial attacks against Large Vision-Language Models (LVLMs) are crucial for exposing safety vulnerabilities in modern multimodal systems. Recent attacks based on input transformations, such as random cropping, suggest that spatially localized perturbations can be more effective than global image manipulation. However, randomly cropping the entire image is inherently stochastic and fails to us… ▽ More Adversarial attacks against Large Vision-Language Models (LVLMs) are crucial for exposing safety vulnerabilities in modern multimodal systems. Recent attacks based on input transformations, such as random cropping, suggest that spatially localized perturbations can be more effective than global image manipulation. However, randomly cropping the entire image is inherently stochastic and fails to use the limited per-pixel perturbation budget efficiently. We make two key observations: (i) regional attention scores are positively correlated with adversarial loss sensitivity, and (ii) attacking high-attention regions induces a structured redistribution of attention toward subsequent salient regions. Based on these findings, we propose Stage-wise Attention-Guided Attack (SAGA), an attention-guided framework that progressively concentrates perturbations on high-attention regions. SAGA enables more efficient use of constrained perturbation budgets, producing highly imperceptible adversarial examples while consistently achieving state-of-the-art attack success rates across ten LVLMs. The source code is available at https://github.com/jackwaky/SAGA. △ Less

Submitted 4 February, 2026; originally announced February 2026.

Comments: Pre-print

SurfSplat: Conquering Feedforward 2D Gaussian Splatting with Surface Continuity Priors

Authors: Bing He, Jingnan Gao, Yunuo Chen, Ning Cao, Gang Chen, Zhengxue Cheng, Li Song, Wenjun Zhang

Abstract: Reconstructing 3D scenes from sparse images remains a challenging task due to the difficulty of recovering accurate geometry and texture without optimization. Recent approaches leverage generalizable models to generate 3D scenes using 3D Gaussian Splatting (3DGS) primitive. However, they often fail to produce continuous surfaces and instead yield discrete, color-biased point clouds that appear pla… ▽ More Reconstructing 3D scenes from sparse images remains a challenging task due to the difficulty of recovering accurate geometry and texture without optimization. Recent approaches leverage generalizable models to generate 3D scenes using 3D Gaussian Splatting (3DGS) primitive. However, they often fail to produce continuous surfaces and instead yield discrete, color-biased point clouds that appear plausible at normal resolution but reveal severe artifacts under close-up views. To address this issue, we present SurfSplat, a feedforward framework based on 2D Gaussian Splatting (2DGS) primitive, which provides stronger anisotropy and higher geometric precision. By incorporating a surface continuity prior and a forced alpha blending strategy, SurfSplat reconstructs coherent geometry together with faithful textures. Furthermore, we introduce High-Resolution Rendering Consistency (HRRC), a new evaluation metric designed to evaluate high-resolution reconstruction quality. Extensive experiments on RealEstate10K, DL3DV, and ScanNet demonstrate that SurfSplat consistently outperforms prior methods on both standard metrics and HRRC, establishing a robust solution for high-fidelity 3D reconstruction from sparse inputs. Project page: https://hebing-sjtu.github.io/SurfSplat-website/ △ Less

Submitted 3 February, 2026; v1 submitted 2 February, 2026; originally announced February 2026.

Comments: ICLR 2026; Project Page: https://hebing-sjtu.github.io/SurfSplat-website/

LLM-Driven Composite Neural Architecture Search for Multi-Source RL State Encoding

Authors: Yu Yu, Qian Xie, Nairen Cao, Li Jin

Abstract: Designing state encoders for reinforcement learning (RL) with multiple information sources -- such as sensor measurements, time-series signals, image observations, and textual instructions -- remains underexplored and often requires manual design. We formalize this challenge as a problem of composite neural architecture search (NAS), where multiple source-specific modules and a fusion module are j… ▽ More Designing state encoders for reinforcement learning (RL) with multiple information sources -- such as sensor measurements, time-series signals, image observations, and textual instructions -- remains underexplored and often requires manual design. We formalize this challenge as a problem of composite neural architecture search (NAS), where multiple source-specific modules and a fusion module are jointly optimized. Existing NAS methods overlook useful side information from the intermediate outputs of these modules -- such as their representation quality -- limiting sample efficiency in multi-source RL settings. To address this, we propose an LLM-driven NAS pipeline in which the LLM serves as a neural architecture design agent, leveraging language-model priors and intermediate-output signals to guide sample-efficient search for high-performing composite state encoders. On a mixed-autonomy traffic control task, our approach discovers higher-performing architectures with fewer candidate evaluations than traditional NAS baselines and the LLM-based GENIUS framework. △ Less

Submitted 11 December, 2025; v1 submitted 7 December, 2025; originally announced December 2025.

Comments: NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning

Designed to Spread: A Generative Approach to Enhance Information Diffusion

Authors: Ziqing Qian, Jiaying Lei, Shengqi Dang, Nan Cao

Abstract: Social media has fundamentally transformed how people access information and form social connections, with content expression playing a critical role in driving information diffusion. While prior research has focused largely on network structures and tipping point identification, it provides limited tools for automatically generating content tailored for virality within a specific audience. To fil… ▽ More Social media has fundamentally transformed how people access information and form social connections, with content expression playing a critical role in driving information diffusion. While prior research has focused largely on network structures and tipping point identification, it provides limited tools for automatically generating content tailored for virality within a specific audience. To fill this gap, we propose the novel task of DOCG and introduce an information enhancement algorithm for generating content optimized for diffusion. Our method includes an influence indicator that enables content-level diffusion assessment without requiring access to network topology, and an information editor that employs reinforcement learning to explore interpretable editing strategies. The editor leverages generative models to produce semantically faithful, audience-aware textual or visual content. Experiments on real-world social media datasets and user study demonstrate that our approach significantly improves diffusion effectiveness while preserving the core semantics of the original content. △ Less

Submitted 12 March, 2026; v1 submitted 16 November, 2025; originally announced November 2025.

Comments: Accepted by AAAI26

DensiCrafter: Physically-Constrained Generation and Fabrication of Self-Supporting Hollow Structures

Authors: Shengqi Dang, Fu Chai, Jiaxin Li, Chao Yuan, Wei Ye, Nan Cao

Abstract: The rise of 3D generative models has enabled automatic 3D geometry and texture synthesis from multimodal inputs (e.g., text or images). However, these methods often ignore physical constraints and manufacturability considerations. In this work, we address the challenge of producing 3D designs that are both lightweight and self-supporting. We present DensiCrafter, a framework for generating lightwe… ▽ More The rise of 3D generative models has enabled automatic 3D geometry and texture synthesis from multimodal inputs (e.g., text or images). However, these methods often ignore physical constraints and manufacturability considerations. In this work, we address the challenge of producing 3D designs that are both lightweight and self-supporting. We present DensiCrafter, a framework for generating lightweight, self-supporting 3D hollow structures by optimizing the density field. Starting from coarse voxel grids produced by Trellis, we interpret these as continuous density fields to optimize and introduce three differentiable, physically constrained, and simulation-free loss terms. Additionally, a mass regularization penalizes unnecessary material, while a restricted optimization domain preserves the outer surface. Our method seamlessly integrates with pretrained Trellis-based models (e.g., Trellis, DSO) without any architectural changes. In extensive evaluations, we achieve up to 43% reduction in material mass on the text-to-3D task. Compared to state-of-the-art baselines, our method could improve the stability and maintain high geometric fidelity. Real-world 3D-printing experiments confirm that our hollow designs can be reliably fabricated and could be self-supporting. △ Less

Submitted 26 November, 2025; v1 submitted 12 November, 2025; originally announced November 2025.

FastUMI-100K: Advancing Data-driven Robotic Manipulation with a Large-scale UMI-style Dataset

Authors: Kehui Liu, Zhongjie Jia, Yang Li, Zhaxizhuoma, Pengan Chen, Song Liu, Xin Liu, Pingrui Zhang, Haoming Song, Xinyi Ye, Nieqing Cao, Zhigang Wang, Jia Zeng, Dong Wang, Yan Ding, Bin Zhao, Xuelong Li

Abstract: Data-driven robotic manipulation learning depends on large-scale, high-quality expert demonstration datasets. However, existing datasets, which primarily rely on human teleoperated robot collection, are limited in terms of scalability, trajectory smoothness, and applicability across different robotic embodiments in real-world environments. In this paper, we present FastUMI-100K, a large-scale UMI-… ▽ More Data-driven robotic manipulation learning depends on large-scale, high-quality expert demonstration datasets. However, existing datasets, which primarily rely on human teleoperated robot collection, are limited in terms of scalability, trajectory smoothness, and applicability across different robotic embodiments in real-world environments. In this paper, we present FastUMI-100K, a large-scale UMI-style multimodal demonstration dataset, designed to overcome these limitations and meet the growing complexity of real-world manipulation tasks. Collected by FastUMI, a novel robotic system featuring a modular, hardware-decoupled mechanical design and an integrated lightweight tracking system, FastUMI-100K offers a more scalable, flexible, and adaptable solution to fulfill the diverse requirements of real-world robot demonstration data. Specifically, FastUMI-100K contains over 100K+ demonstration trajectories collected across representative household environments, covering 54 tasks and hundreds of object types. Our dataset integrates multimodal streams, including end-effector states, multi-view wrist-mounted fisheye images and textual annotations. Each trajectory has a length ranging from 120 to 500 frames. Experimental results demonstrate that FastUMI-100K enables high policy success rates across various baseline algorithms, confirming its robustness, adaptability, and real-world applicability for solving complex, dynamic manipulation challenges. The source code and dataset will be released in this link https://github.com/MrKeee/FastUMI-100K. △ Less

Submitted 9 October, 2025; originally announced October 2025.

4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming

Authors: Zihan Zheng, Zhenlong Wu, Houqiang Zhong, Yuan Tian, Ning Cao, Lan Xu, Jiangchao Yao, Xiaoyun Zhang, Qiang Hu, Wenjun Zhang

Abstract: Achieving seamless viewing of high-fidelity volumetric video, comparable to 2D video experiences, remains an open challenge. Existing volumetric video compression methods either lack the flexibility to adjust quality and bitrate within a single model for efficient streaming across diverse networks and devices, or struggle with real-time decoding and rendering on lightweight mobile platforms. To ad… ▽ More Achieving seamless viewing of high-fidelity volumetric video, comparable to 2D video experiences, remains an open challenge. Existing volumetric video compression methods either lack the flexibility to adjust quality and bitrate within a single model for efficient streaming across diverse networks and devices, or struggle with real-time decoding and rendering on lightweight mobile platforms. To address these challenges, we introduce 4DGCPro, a novel hierarchical 4D Gaussian compression framework that facilitates real-time mobile decoding and high-quality rendering via progressive volumetric video streaming in a single bitstream. Specifically, we propose a perceptually-weighted and compression-friendly hierarchical 4D Gaussian representation with motion-aware adaptive grouping to reduce temporal redundancy, preserve coherence, and enable scalable multi-level detail streaming. Furthermore, we present an end-to-end entropy-optimized training scheme, which incorporates layer-wise rate-distortion (RD) supervision and attribute-specific entropy modeling for efficient bitstream generation. Extensive experiments show that 4DGCPro enables flexible quality and multiple bitrate within a single model, achieving real-time decoding and rendering on mobile devices while outperforming existing methods in RD performance across multiple datasets. Project Page: https://mediax-sjtu.github.io/4DGCPro △ Less

Submitted 26 September, 2025; v1 submitted 22 September, 2025; originally announced September 2025.

Comments: NeurIPS 2025

4D-MoDe: Towards Editable and Scalable Volumetric Streaming via Motion-Decoupled 4D Gaussian Compression

Authors: Houqiang Zhong, Zihan Zheng, Qiang Hu, Yuan Tian, Ning Cao, Lan Xu, Xiaoyun Zhang, Zhengxue Cheng, Li Song, Wenjun Zhang

Abstract: Volumetric video has emerged as a key medium for immersive telepresence and augmented/virtual reality, enabling six-degrees-of-freedom (6DoF) navigation and realistic spatial interactions. However, delivering high-quality dynamic volumetric content at scale remains challenging due to massive data volume, complex motion, and limited editability of existing representations. In this paper, we present… ▽ More Volumetric video has emerged as a key medium for immersive telepresence and augmented/virtual reality, enabling six-degrees-of-freedom (6DoF) navigation and realistic spatial interactions. However, delivering high-quality dynamic volumetric content at scale remains challenging due to massive data volume, complex motion, and limited editability of existing representations. In this paper, we present 4D-MoDe, a motion-decoupled 4D Gaussian compression framework designed for scalable and editable volumetric video streaming. Our method introduces a layered representation that explicitly separates static backgrounds from dynamic foregrounds using a lookahead-based motion decomposition strategy, significantly reducing temporal redundancy and enabling selective background/foreground streaming. To capture continuous motion trajectories, we employ a multi-resolution motion estimation grid and a lightweight shared MLP, complemented by a dynamic Gaussian compensation mechanism to model emergent content. An adaptive grouping scheme dynamically inserts background keyframes to balance temporal consistency and compression efficiency. Furthermore, an entropy-aware training pipeline jointly optimizes the motion fields and Gaussian parameters under a rate-distortion (RD) objective, while employing range-based and KD-tree compression to minimize storage overhead. Extensive experiments on multiple datasets demonstrate that 4D-MoDe consistently achieves competitive reconstruction quality with an order of magnitude lower storage cost (e.g., as low as \textbf{11.4} KB/frame) compared to state-of-the-art methods, while supporting practical applications such as background replacement and foreground-only streaming. △ Less

Submitted 22 September, 2025; originally announced September 2025.

Funding the Frontier: Visualizing the Broad Impact of Science and Science Funding

Authors: Yifang Wang, Yifan Qian, Xiaoyu Qi, Yian Yin, Shengqi Dang, Ziqing Qian, Benjamin F. Jones, Nan Cao, Dashun Wang

Abstract: Understanding the broad impact of science and science funding is critical to ensuring that science investments and policies align with societal needs. Existing research links science funding to the output of scientific publications but largely leaves out the downstream uses of science and the myriad ways in which investing in science may impact human society. As funders seek to allocate scarce fun… ▽ More Understanding the broad impact of science and science funding is critical to ensuring that science investments and policies align with societal needs. Existing research links science funding to the output of scientific publications but largely leaves out the downstream uses of science and the myriad ways in which investing in science may impact human society. As funders seek to allocate scarce funding resources across a complex research landscape, there is an urgent need for informative and transparent tools that allow for comprehensive assessments and visualization of the impact of funding. Here we present Funding the Frontier (FtF), a visual analysis system for researchers, funders, policymakers, university leaders, and the broad public to analyze multidimensional impacts of funding and make informed decisions regarding research investments and opportunities. The system is built on a massive data collection that connects 7M research grants to 140M scientific publications, 160M patents, 10.9M policy documents, 800K clinical trials, and 5.8M newsfeeds, with 1.8B citation linkages among these entities, systematically linking science funding to its downstream impacts. As such, Funding the Frontier is distinguished by its multifaceted impact analysis framework. The system incorporates diverse impact metrics and predictive models that forecast future investment opportunities into an array of coordinated views, allowing for easy exploration of funding and its outcomes. We evaluate the effectiveness and usability of the system using case studies and expert interviews. Feedback suggests that our system not only fulfills the primary analysis needs of its target users, but the rich datasets of the complex science ecosystem and the proposed analysis framework also open new avenues for both visualization and the science of science research. △ Less

Submitted 19 September, 2025; originally announced September 2025.

TexVerse: A Universe of 3D Objects with High-Resolution Textures

Authors: Yibo Zhang, Li Zhang, Rui Ma, Nan Cao

Abstract: We introduce TexVerse, a large-scale 3D dataset featuring high-resolution textures. While recent advances in large-scale 3D datasets have enhanced high-resolution geometry generation, creating high-resolution textures end-to-end remains underexplored due to the lack of suitable datasets. TexVerse fills this gap with a curated collection of over 858K unique high-resolution 3D models sourced from Sk… ▽ More We introduce TexVerse, a large-scale 3D dataset featuring high-resolution textures. While recent advances in large-scale 3D datasets have enhanced high-resolution geometry generation, creating high-resolution textures end-to-end remains underexplored due to the lack of suitable datasets. TexVerse fills this gap with a curated collection of over 858K unique high-resolution 3D models sourced from Sketchfab, including more than 158K models with physically based rendering (PBR) materials. Each model encompasses all of its high-resolution variants, bringing the total to 1.6M 3D instances. TexVerse also includes specialized subsets: TexVerse-Skeleton, with 69K rigged models, and TexVerse-Animation, with 54K animated models, both preserving original skeleton and animation data uploaded by the user. We also provide detailed model annotations describing overall characteristics, structural components, and intricate features. TexVerse offers a high-quality data resource with wide-ranging potential applications in texture synthesis, PBR material development, animation, and various 3D vision and graphics tasks. △ Less

Submitted 3 September, 2025; v1 submitted 14 August, 2025; originally announced August 2025.

Comments: https://github.com/yiboz2001/TexVerse

Data-Driven Discovery of Mobility Periodicity for Understanding Urban Systems

Authors: Xinyu Chen, Qi Wang, Yunhan Zheng, Nina Cao, HanQin Cai, Jinhua Zhao

Abstract: Human mobility regularity is crucial for understanding urban dynamics and informing decision-making processes. This study first quantifies the periodicity in complex human mobility data as a sparse identification of dominant positive auto-correlations in time series autoregression and then discovers periodic patterns. We apply the framework to large-scale metro passenger flow data in Hangzhou, Chi… ▽ More Human mobility regularity is crucial for understanding urban dynamics and informing decision-making processes. This study first quantifies the periodicity in complex human mobility data as a sparse identification of dominant positive auto-correlations in time series autoregression and then discovers periodic patterns. We apply the framework to large-scale metro passenger flow data in Hangzhou, China and multi-modal mobility data in New York City and Chicago, USA, revealing the interpretable weekly periodicity across different spatial locations over past several years. The analysis of ridesharing data from 2019 to 2024 demonstrates the disruptive impact of the pandemic on mobility regularity and the subsequent recovery trends. In 2024, the periodic mobility patterns of ridesharing, taxi, subway, and bikesharing in Manhattan uncover the regularity and variability of these travel modes. Our findings highlight the potential of interpretable machine learning to discover spatiotemporal mobility patterns and offer a valuable tool for understanding urban systems. △ Less

Submitted 12 September, 2025; v1 submitted 2 August, 2025; originally announced August 2025.

Robust ID-Specific Face Restoration via Alignment Learning

Authors: Yushun Fang, Lu Liu, Xiang Gao, Qiang Hu, Ning Cao, Jianghe Cui, Gang Chen, Xiaoyun Zhang

Abstract: The latest developments in Face Restoration have yielded significant advancements in visual quality through the utilization of diverse diffusion priors. Nevertheless, the uncertainty of face identity introduced by identity-obscure inputs and stochastic generative processes remains unresolved. To address this challenge, we present Robust ID-Specific Face Restoration (RIDFR), a novel ID-specific fac… ▽ More The latest developments in Face Restoration have yielded significant advancements in visual quality through the utilization of diverse diffusion priors. Nevertheless, the uncertainty of face identity introduced by identity-obscure inputs and stochastic generative processes remains unresolved. To address this challenge, we present Robust ID-Specific Face Restoration (RIDFR), a novel ID-specific face restoration framework based on diffusion models. Specifically, RIDFR leverages a pre-trained diffusion model in conjunction with two parallel conditioning modules. The Content Injection Module inputs the severely degraded image, while the Identity Injection Module integrates the specific identity from a given image. Subsequently, RIDFR incorporates Alignment Learning, which aligns the restoration results from multiple references with the same identity in order to suppress the interference of ID-irrelevant face semantics (e.g. pose, expression, make-up, hair style). Experiments demonstrate that our framework outperforms the state-of-the-art methods, reconstructing high-quality ID-specific results with high identity fidelity and demonstrating strong robustness. △ Less

Submitted 28 August, 2025; v1 submitted 14 July, 2025; originally announced July 2025.

Comments: PRCV2025 Accepted

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Authors: Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, Krishna Haridasan, Ahmed Omran, Nikunj Saunshi, Dara Bahri, Gaurav Mishra, Eric Chu , et al. (3410 additional authors not shown)

Abstract: In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal unde… ▽ More In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving. △ Less

Submitted 19 December, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Comments: 72 pages, 17 figures

CODS : A Theoretical Model for Computational Design Based on Design Space

Authors: Nan Cao, Xiaoyu Qi, Chuer Chen, Xiaoke Yan

Abstract: We introduce CODS (Computational Optimization in Design Space), a theoretical model that frames computational design as a constrained optimization problem over a structured, multi-dimensional design space. Unlike existing methods that rely on handcrafted heuristics or domain-specific rules, CODS provides a generalizable and interpretable framework that supports diverse design tasks. Given a user r… ▽ More We introduce CODS (Computational Optimization in Design Space), a theoretical model that frames computational design as a constrained optimization problem over a structured, multi-dimensional design space. Unlike existing methods that rely on handcrafted heuristics or domain-specific rules, CODS provides a generalizable and interpretable framework that supports diverse design tasks. Given a user requirement and a well-defined design space, CODS automatically derives soft and hard constraints using large language models through a structured prompt engineering pipeline. These constraints guide the optimization process to generate design solutions that are coherent, expressive, and aligned with user intent. We validate our approach across two domains-visualization design and knitwear generation-demonstrating superior performance in design quality, intent alignment, and user preference compared to existing LLM-based methods. CODS offers a unified foundation for scalable, controllable, and AI-powered design automation. △ Less

Submitted 23 June, 2025; originally announced June 2025.

ChartBlender: An Interactive System for Authoring and Synchronizing Visualization Charts in Video

Authors: Yi He, Yuqi Liu, Chenpu Li, Ruoyan Chen, Chuer Chen, Shengqi Dang, Nan Cao

Abstract: Embedding data visualizations in video can enhance the communication of complex information. However, this process is often labor-intensive, requiring designers to adjust visualizations frame by frame manually. In this work, we present ChartBlender, a novel system that streamlines this process by enabling users to create data visualizations, embed them seamlessly into video scenes, and automatical… ▽ More Embedding data visualizations in video can enhance the communication of complex information. However, this process is often labor-intensive, requiring designers to adjust visualizations frame by frame manually. In this work, we present ChartBlender, a novel system that streamlines this process by enabling users to create data visualizations, embed them seamlessly into video scenes, and automatically synchronize them with both camera motion and moving objects. Particularly, ChartBlender incorporates a tracking algorithm that supports both object and camera tracking, ensuring robust alignment of visualizations with dynamic video content. To maintain visual clarity and aesthetic coherence, we also explore the design space of video-suited visualizations and develop a library of customizable templates optimized for video embedding. We evaluate \oursName\ChartBlender through two controlled experiments and expert interviews with five domain experts. Results show that our system enables accurate synchronization and accelerates the production of data-driven videos. △ Less

Submitted 30 December, 2025; v1 submitted 16 June, 2025; originally announced June 2025.

Comments: 12 pages, 8 figures

IDEA: Augmenting Design Intelligence through Design Space Exploration

Authors: Chuer Chen, Xiaoke Yan, Xiaoyu Qi, Nan Cao

Abstract: Design spaces serve as a conceptual framework that enables designers to explore feasible solutions through the selection and combination of design elements. However, effective decision-making remains heavily dependent on the designer's experience, and the absence of mathematical formalization prevents computational support for automated design processes. To bridge this gap, we introduce a structur… ▽ More Design spaces serve as a conceptual framework that enables designers to explore feasible solutions through the selection and combination of design elements. However, effective decision-making remains heavily dependent on the designer's experience, and the absence of mathematical formalization prevents computational support for automated design processes. To bridge this gap, we introduce a structured representation that models design spaces with orthogonal dimensions and discrete selectable elements. Building on this model, we present IDEA, a decision-making framework for augmenting design intelligence through design space exploration to generate effective outcomes. Specifically, IDEA leverages large language models (LLMs) for constraint generation, incorporates a Monte Carlo Tree Search (MCTS) algorithm guided by these constraints to explore the design space efficiently, and instantiates abstract decisions into domain-specific implementations. We validate IDEA in two design scenarios: data-driven article composition and pictorial visualization generation, supported by example results, expert interviews, and a user study. The evaluation demonstrates the IDEA's adaptability across domains and its capability to produce superior design outcomes. △ Less

Submitted 12 June, 2025; originally announced June 2025.

Person Re-Identification System at Semantic Level based on Pedestrian Attributes Ontology

Authors: Ngoc Q. Ly, Hieu N. M. Cao, Thi T. Nguyen

Abstract: Person Re-Identification (Re-ID) is a very important task in video surveillance systems such as tracking people, finding people in public places, or analysing customer behavior in supermarkets. Although there have been many works to solve this problem, there are still remaining challenges such as large-scale datasets, imbalanced data, viewpoint, fine grained data (attributes), the Local Features a… ▽ More Person Re-Identification (Re-ID) is a very important task in video surveillance systems such as tracking people, finding people in public places, or analysing customer behavior in supermarkets. Although there have been many works to solve this problem, there are still remaining challenges such as large-scale datasets, imbalanced data, viewpoint, fine grained data (attributes), the Local Features are not employed at semantic level in online stage of Re-ID task, furthermore, the imbalanced data problem of attributes are not taken into consideration. This paper has proposed a Unified Re-ID system consisted of three main modules such as Pedestrian Attribute Ontology (PAO), Local Multi-task DCNN (Local MDCNN), Imbalance Data Solver (IDS). The new main point of our Re-ID system is the power of mutual support of PAO, Local MDCNN and IDS to exploit the inner-group correlations of attributes and pre-filter the mismatch candidates from Gallery set based on semantic information as Fashion Attributes and Facial Attributes, to solve the imbalanced data of attributes without adjusting network architecture and data augmentation. We experimented on the well-known Market1501 dataset. The experimental results have shown the effectiveness of our Re-ID system and it could achieve the higher performance on Market1501 dataset in comparison to some state-of-the-art Re-ID methods. △ Less

Submitted 4 June, 2025; originally announced June 2025.

Journal ref: International Journal of Advanced Computer Science and Applications(IJACSA), 11(2), 2020

Mixture-of-Experts for Personalized and Semantic-Aware Next Location Prediction

Authors: Shuai Liu, Ning Cao, Yile Chen, Yue Jiang, Gao Cong

Abstract: Next location prediction plays a critical role in understanding human mobility patterns. However, existing approaches face two core limitations: (1) they fall short in capturing the complex, multi-functional semantics of real-world locations; and (2) they lack the capacity to model heterogeneous behavioral dynamics across diverse user groups. To tackle these challenges, we introduce NextLocMoE, a… ▽ More Next location prediction plays a critical role in understanding human mobility patterns. However, existing approaches face two core limitations: (1) they fall short in capturing the complex, multi-functional semantics of real-world locations; and (2) they lack the capacity to model heterogeneous behavioral dynamics across diverse user groups. To tackle these challenges, we introduce NextLocMoE, a novel framework built upon large language models (LLMs) and structured around a dual-level Mixture-of-Experts (MoE) design. Our architecture comprises two specialized modules: a Location Semantics MoE that operates at the embedding level to encode rich functional semantics of locations, and a Personalized MoE embedded within the Transformer backbone to dynamically adapt to individual user mobility patterns. In addition, we incorporate a history-aware routing mechanism that leverages long-term trajectory data to enhance expert selection and ensure prediction stability. Empirical evaluations across several real-world urban datasets show that NextLocMoE achieves superior performance in terms of predictive accuracy, cross-domain generalization, and interpretability △ Less

Submitted 30 May, 2025; originally announced May 2025.

UniTalk: Towards Universal Active Speaker Detection in Real World Scenarios

Authors: Le Thien Phuc Nguyen, Zhuoran Yu, Khoa Quang Nhat Cao, Yuwei Guo, Tu Ho Manh Pham, Tuan Tai Nguyen, Toan Ngo Duc Vo, Lucas Poon, Soochahn Lee, Yong Jae Lee

Abstract: We present UniTalk, a novel dataset specifically designed for the task of active speaker detection, emphasizing challenging scenarios to enhance model generalization. Unlike previously established benchmarks such as AVA, which predominantly features old movies and thus exhibits significant domain gaps, UniTalk focuses explicitly on diverse and difficult real-world conditions. These include underre… ▽ More We present UniTalk, a novel dataset specifically designed for the task of active speaker detection, emphasizing challenging scenarios to enhance model generalization. Unlike previously established benchmarks such as AVA, which predominantly features old movies and thus exhibits significant domain gaps, UniTalk focuses explicitly on diverse and difficult real-world conditions. These include underrepresented languages, noisy backgrounds, and crowded scenes - such as multiple visible speakers speaking concurrently or in overlapping turns. It contains over 44.5 hours of video with frame-level active speaker annotations across 48,693 speaking identities, and spans a broad range of video types that reflect real-world conditions. Through rigorous evaluation, we show that state-of-the-art models, while achieving nearly perfect scores on AVA, fail to reach saturation on UniTalk, suggesting that the ASD task remains far from solved under realistic conditions. Nevertheless, models trained on UniTalk demonstrate stronger generalization to modern "in-the-wild" datasets like Talkies and ASW, as well as to AVA. UniTalk thus establishes a new benchmark for active speaker detection, providing researchers with a valuable resource for developing and evaluating versatile and resilient models. Dataset: https://huggingface.co/datasets/plnguyen2908/UniTalk-ASD Code: https://github.com/plnguyen2908/UniTalk-ASD-code △ Less

Submitted 28 May, 2025; originally announced May 2025.

DataScout: Automatic Data Fact Retrieval for Statement Augmentation with an LLM-Based Agent

Authors: Chuer Chen, Yuqi Liu, Danqing Shi, Shixiong Cao, Nan Cao

Abstract: A data story typically integrates data facts from multiple perspectives and stances to construct a comprehensive and objective narrative. However, retrieving these facts demands time for data search and challenges the creator's analytical skills. In this work, we introduce DataScout, an interactive system that automatically performs reasoning and stance-based data facts retrieval to augment the us… ▽ More A data story typically integrates data facts from multiple perspectives and stances to construct a comprehensive and objective narrative. However, retrieving these facts demands time for data search and challenges the creator's analytical skills. In this work, we introduce DataScout, an interactive system that automatically performs reasoning and stance-based data facts retrieval to augment the user's statement. Particularly, DataScout leverages an LLM-based agent to construct a retrieval tree, enabling collaborative control of its expansion between users and the agent. The interface visualizes the retrieval tree as a mind map that eases users to intuitively steer the retrieval direction and effectively engage in reasoning and analysis. We evaluate the proposed system through case studies and in-depth expert interviews. Our evaluation demonstrates that DataScout can effectively retrieve multifaceted data facts from different stances, helping users verify their statements and enhance the credibility of their stories. △ Less

Submitted 24 April, 2025; originally announced April 2025.

MV-Crafter: An Intelligent System for Music-guided Video Generation

Authors: Chuer Chen, Shengqi Dang, Yuqi Liu, Nanxuan Zhao, Yang Shi, Nan Cao

Abstract: Music videos, as a prevalent form of multimedia entertainment, deliver engaging audio-visual experiences to audiences and have gained immense popularity among singers and fans. Creators can express their interpretations of music naturally through visual elements. However, the creation process of music video demands proficiency in script design, video shooting, and music-video synchronization, posi… ▽ More Music videos, as a prevalent form of multimedia entertainment, deliver engaging audio-visual experiences to audiences and have gained immense popularity among singers and fans. Creators can express their interpretations of music naturally through visual elements. However, the creation process of music video demands proficiency in script design, video shooting, and music-video synchronization, posing significant challenges for non-professionals. Previous work has designed automated music video generation frameworks. However, they suffer from complexity in input and poor output quality. In response, we present MV-Crafter, a system capable of producing high-quality music videos with synchronized music-video rhythm and style. Our approach involves three technical modules that simulate the human creation process: the script generation module, video generation module, and music-video synchronization module. MV-Crafter leverages a large language model to generate scripts considering the musical semantics. To address the challenge of synchronizing short video clips with music of varying lengths, we propose a dynamic beat matching algorithm and visual envelope-induced warping method to ensure precise, monotonic music-video synchronization. Besides, we design a user-friendly interface to simplify the creation process with intuitive editing features. Extensive experiments have demonstrated that MV-Crafter provides an effective solution for improving the quality of generated music videos. △ Less

Submitted 24 April, 2025; originally announced April 2025.

Static to Dynamic Correlation Clustering

Authors: Nairen Cao, Vincent Cohen-Addad, Euiwoong Lee, Shi Li, David Rasmussen Lolck, Alantha Newman, Mikkel Thorup, Lukas Vogl, Shuyi Yan, Hanwen Zhang

Abstract: Correlation clustering is a well-studied problem, first proposed by Bansal, Blum, and Chawla [BBC04]. The input is an unweighted, undirected graph. The problem is to cluster the vertices so as to minimizing the number of edges between vertices in different clusters and missing edges between vertices inside the same cluster. This problem has a wide application in data mining and machine learning. W… ▽ More Correlation clustering is a well-studied problem, first proposed by Bansal, Blum, and Chawla [BBC04]. The input is an unweighted, undirected graph. The problem is to cluster the vertices so as to minimizing the number of edges between vertices in different clusters and missing edges between vertices inside the same cluster. This problem has a wide application in data mining and machine learning. We introduce a general framework that transforms existing static correlation clustering algorithms into fully-dynamic ones that work against an adaptive adversary. We show how to apply our framework to known efficient correlation clustering algorithms, starting from the classic $3$-approximate Pivot algorithm from [ACN08]. Applied to the most recent near-linear $1.437$-approximation algorithm from [CCL+25], we get a $1.437$-approximation fully-dynamic algorithm that works with worst-case constant update time. The original static algorithm gets its approximation factor with constant probability, and we get the same against an adaptive adversary in the sense that for any given update step not known to our algorithm, our solution is a $1.437$-approximation with constant probability when we reach this update. Previous dynamic algorithms had approximation factors around $3$ in expectation, and they could only handle an oblivious adversary. △ Less

Submitted 22 April, 2025; v1 submitted 16 April, 2025; originally announced April 2025.

An In-Situ Spatial-Temporal Sequence Detector for Neuromorphic Vision Sensor Empowered by High Density Vertical NAND Storage

Authors: Zijian Zhao, Varun Darshana Parekh, Po-Kai Hsu, Yixin Qin, Yiming Song, A N M Nafiul Islam, Ningyuan Cao, Siddharth Joshi, Thomas Kämpfe, Moonyoung Jung, Kwangyou Seo, Kwangsoo Kim, Wanki Kim, Daewon Ha, Sourav Dutta, Abhronil Sengupta, Xiao Gong, Shimeng Yu, Vijaykrishnan Narayanan, Kai Ni

Abstract: Neuromorphic vision sensors require efficient real-time pattern recognition, yet conventional architectures struggle with energy and latency constraints. Here, we present a novel in-situ spatiotemporal sequence detector that leverages vertical NAND storage to achieve massively parallel pattern detection. By encoding each cell with two single-transistor-based multi-level cell (MLC) memory elements,… ▽ More Neuromorphic vision sensors require efficient real-time pattern recognition, yet conventional architectures struggle with energy and latency constraints. Here, we present a novel in-situ spatiotemporal sequence detector that leverages vertical NAND storage to achieve massively parallel pattern detection. By encoding each cell with two single-transistor-based multi-level cell (MLC) memory elements, such as ferroelectric field-effect transistors (FeFETs), and mapping a pixel's temporal sequence onto consecutive word lines (WLs), we enable direct temporal pattern detection within NAND strings. Each NAND string serves as a dedicated reference for a single pixel, while different blocks store patterns for distinct pixels, allowing large-scale spatial-temporal pattern recognition via simple direct bit-line (BL) sensing, a well-established operation in vertical NAND storage. We experimentally validate our approach at both the cell and array levels, demonstrating that vertical NAND-based detector achieves more than six orders of magnitude improvement in energy efficiency and more than three orders of magnitude reduction in latency compared to conventional CPU-based methods. These findings establish vertical NAND storage as a scalable and energy-efficient solution for next-generation neuromorphic vision processing. △ Less

Submitted 30 March, 2025; originally announced March 2025.

Comments: 26 pages, 7 figures

Solving the Correlation Cluster LP in Sublinear Time

Authors: Nairen Cao, Vincent Cohen-Addad, Shi Li, Euiwoong Lee, David Rasmussen Lolck, Alantha Newman, Mikkel Thorup, Lukas Vogl, Shuyi Yan, Hanwen Zhang

Abstract: Correlation Clustering is a fundamental and widely-studied problem in unsupervised learning and data mining. The input is a graph and the goal is to construct a clustering minimizing the number of inter-cluster edges plus the number of missing intra-cluster edges. CCL+24 introduced the cluster LP for Correlation Clustering, which they argued captures the problem much more succinctly than previou… ▽ More Correlation Clustering is a fundamental and widely-studied problem in unsupervised learning and data mining. The input is a graph and the goal is to construct a clustering minimizing the number of inter-cluster edges plus the number of missing intra-cluster edges. CCL+24 introduced the cluster LP for Correlation Clustering, which they argued captures the problem much more succinctly than previous linear programming formulations. However, the cluster LP has exponential size, with a variable for every possible set of vertices in the input graph. Nevertheless, CCL+24 showed how to find a feasible solution for the cluster LP in time $O(n^{\text{poly}(1/ε)})$ with objective value at most $(1+ε)$ times the value of an optimal solution for the respective Correlation Clustering instance. Furthermore, they showed how to round a solution to the cluster LP, yielding a $(1.485+ε)$-approximation algorithm for the Correlation Clustering problem. The main technical result of this paper is a new approach to find a feasible solution for the cluster LP with objective value at most $(1+ε)$ of the optimum in time $\widetilde O(2^{\text{poly}(1/ε)} n)$, where $n$ is the number of vertices in the graph. We also show how to implement the rounding within the same time bounds, thus achieving a fast $(1.485+ε)$-approximation algorithm for the Correlation Clustering problem. This bridges the gap between state-of-the-art methods for approximating Correlation Clustering and the recent focus on fast algorithms. △ Less

Submitted 4 November, 2025; v1 submitted 26 March, 2025; originally announced March 2025.

Large Language Model for Lossless Image Compression with Visual Prompts

Authors: Junhao Du, Chuqin Zhou, Ning Cao, Gang Chen, Yunuo Chen, Zhengxue Cheng, Li Song, Guo Lu, Wenjun Zhang

Abstract: Recent advancements in deep learning have driven significant progress in lossless image compression. With the emergence of Large Language Models (LLMs), preliminary attempts have been made to leverage the extensive prior knowledge embedded in these pretrained models to enhance lossless image compression, particularly by improving the entropy model. However, a significant challenge remains in bridg… ▽ More Recent advancements in deep learning have driven significant progress in lossless image compression. With the emergence of Large Language Models (LLMs), preliminary attempts have been made to leverage the extensive prior knowledge embedded in these pretrained models to enhance lossless image compression, particularly by improving the entropy model. However, a significant challenge remains in bridging the gap between the textual prior knowledge within LLMs and lossless image compression. To tackle this challenge and unlock the potential of LLMs, this paper introduces a novel paradigm for lossless image compression that incorporates LLMs with visual prompts. Specifically, we first generate a lossy reconstruction of the input image as visual prompts, from which we extract features to serve as visual embeddings for the LLM. The residual between the original image and the lossy reconstruction is then fed into the LLM along with these visual embeddings, enabling the LLM to function as an entropy model to predict the probability distribution of the residual. Extensive experiments on multiple benchmark datasets demonstrate our method achieves state-of-the-art compression performance, surpassing both traditional and learning-based lossless image codecs. Furthermore, our approach can be easily extended to images from other domains, such as medical and screen content images, achieving impressive performance. These results highlight the potential of LLMs for lossless image compression and may inspire further research in related directions. △ Less

Submitted 22 February, 2025; originally announced February 2025.

Emotion-Aware Design: Modulating Valence, Arousal, and Dominance in Communication via Design

Authors: Shixiong Cao, Nan Cao

Abstract: In an era of emotionally saturated digital media and information overload, effective communication demands more than clarity and accuracy-it requires emotional awareness. This review introduces the paradigm of emotion-aware design, a framework grounded in the valence-arousal-dominance (VAD) model of affect, which systematically examines how emotional modulation shapes comprehension, memory, and be… ▽ More In an era of emotionally saturated digital media and information overload, effective communication demands more than clarity and accuracy-it requires emotional awareness. This review introduces the paradigm of emotion-aware design, a framework grounded in the valence-arousal-dominance (VAD) model of affect, which systematically examines how emotional modulation shapes comprehension, memory, and behavior. Drawing on insights from psychology, neuroscience, communication, and design, we show that emotional responses significantly influence how information is perceived, retained, and shared. We further propose a multimodal design space-encompassing text, visuals, audio, and interaction-that enables strategic regulation of emotional dimensions to enhance communication efficacy. By linking emotional dynamics to cognitive outcomes and practical design strategies, this review offers both a conceptual foundation and an applied roadmap for designing emotionally resonant communication across domains such as education, health, media, and public discourse. △ Less

Submitted 25 June, 2025; v1 submitted 21 February, 2025; originally announced February 2025.

Comments: 17 pages,6 figures

Min-Max Correlation Clustering via Neighborhood Similarity

Authors: Nairen Cao, Steven Roche, Hsin-Hao Su

Abstract: We present an efficient algorithm for the min-max correlation clustering problem. The input is a complete graph where edges are labeled as either positive $(+)$ or negative $(-)$, and the objective is to find a clustering that minimizes the $\ell_{\infty}$-norm of the disagreement vector over all vertices. We resolve this problem with an efficient $(3 + ε)$-approximation algorithm that runs in n… ▽ More We present an efficient algorithm for the min-max correlation clustering problem. The input is a complete graph where edges are labeled as either positive $(+)$ or negative $(-)$, and the objective is to find a clustering that minimizes the $\ell_{\infty}$-norm of the disagreement vector over all vertices. We resolve this problem with an efficient $(3 + ε)$-approximation algorithm that runs in nearly linear time, $\tilde{O}(|E^+|)$, where $|E^+|$ denotes the number of positive edges. This improves upon the previous best-known approximation guarantee of 4 by Heidrich, Irmai, and Andres, whose algorithm runs in $O(|V|^2 + |V| D^2)$ time, where $|V|$ is the number of nodes and $D$ is the maximum degree in the graph. Furthermore, we extend our algorithm to the massively parallel computation (MPC) model and the semi-streaming model. In the MPC model, our algorithm runs on machines with memory sublinear in the number of nodes and takes $O(1)$ rounds. In the streaming model, our algorithm requires only $\tilde{O}(|V|)$ space, where $|V|$ is the number of vertices in the graph. Our algorithms are purely combinatorial. They are based on a novel structural observation about the optimal min-max instance, which enables the construction of a $(3 + ε)$-approximation algorithm using $O(|E^+|)$ neighborhood similarity queries. By leveraging random projection, we further show these queries can be computed in nearly linear time. △ Less

Submitted 17 February, 2025; originally announced February 2025.

EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model

Authors: Shengqi Dang, Yi He, Long Ling, Ziqing Qian, Nanxuan Zhao, Nan Cao

Abstract: Recent research shows that emotions can enhance users' cognition and influence information communication. While research on visual emotion analysis is extensive, limited work has been done on helping users generate emotionally rich image content. Existing work on emotional image generation relies on discrete emotion categories, making it challenging to capture complex and subtle emotional nuances… ▽ More Recent research shows that emotions can enhance users' cognition and influence information communication. While research on visual emotion analysis is extensive, limited work has been done on helping users generate emotionally rich image content. Existing work on emotional image generation relies on discrete emotion categories, making it challenging to capture complex and subtle emotional nuances accurately. Additionally, these methods struggle to control the specific content of generated images based on text prompts. In this work, we introduce the new task of continuous emotional image content generation (C-EICG) and present EmotiCrafter, an emotional image generation model that generates images based on text prompts and Valence-Arousal values. Specifically, we propose a novel emotion-embedding mapping network that embeds Valence-Arousal values into textual features, enabling the capture of specific emotions in alignment with intended input prompts. Additionally, we introduce a loss function to enhance emotion expression. The experimental results show that our method effectively generates images representing specific emotions with the desired content and outperforms existing techniques. △ Less

Submitted 30 December, 2025; v1 submitted 9 January, 2025; originally announced January 2025.

Comments: 11 pages, 10 figures

A 65 nm Bayesian Neural Network Accelerator with 360 fJ/Sample In-Word GRNG for AI Uncertainty Estimation

Authors: Zephan M. Enciso, Boyang Cheng, Likai Pei, Jianbo Liu, Steven Davis, Michael Niemier, Ningyuan Cao

Abstract: Uncertainty estimation is an indispensable capability for AI-enabled, safety-critical applications, e.g. autonomous vehicles or medical diagnosis. Bayesian neural networks (BNNs) use Bayesian statistics to provide both classification predictions and uncertainty estimation, but they suffer from high computational overhead associated with random number generation and repeated sample iterations. Furt… ▽ More Uncertainty estimation is an indispensable capability for AI-enabled, safety-critical applications, e.g. autonomous vehicles or medical diagnosis. Bayesian neural networks (BNNs) use Bayesian statistics to provide both classification predictions and uncertainty estimation, but they suffer from high computational overhead associated with random number generation and repeated sample iterations. Furthermore, BNNs are not immediately amenable to acceleration through compute-in-memory architectures due to the frequent memory writes necessary after each RNG operation. To address these challenges, we present an ASIC that integrates 360 fJ/Sample Gaussian RNG directly into the SRAM memory words. This integration reduces RNG overhead and enables fully-parallel compute-in-memory operations for BNNs. The prototype chip achieves 5.12 GSa/s RNG throughput and 102 GOp/s neural network throughput while occupying 0.45 mm2, bringing AI uncertainty estimation to edge computation. △ Less

Submitted 22 January, 2025; v1 submitted 8 January, 2025; originally announced January 2025.

Comments: 7 pages, 12 figures

ACM Class: B.7.1; B.3.1; I.2.10; I.2.9

Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph

Authors: Yutong Zhang, Lixing Chen, Shenghong Li, Nan Cao, Yang Shi, Jiaxin Ding, Zhe Qu, Pan Zhou, Yang Bai

Abstract: Large language models (LLMs) have demonstrated exceptional performance across a wide variety of domains. Nonetheless, generalist LLMs continue to fall short in reasoning tasks necessitating specialized knowledge. Prior investigations into specialized LLMs focused on domain-specific training, which entails substantial efforts in domain data acquisition and model parameter fine-tuning. To address th… ▽ More Large language models (LLMs) have demonstrated exceptional performance across a wide variety of domains. Nonetheless, generalist LLMs continue to fall short in reasoning tasks necessitating specialized knowledge. Prior investigations into specialized LLMs focused on domain-specific training, which entails substantial efforts in domain data acquisition and model parameter fine-tuning. To address these challenges, this paper proposes the Way-to-Specialist (WTS) framework, which synergizes retrieval-augmented generation with knowledge graphs (KGs) to enhance the specialized capability of LLMs in the absence of specialized training. In distinction to existing paradigms that merely utilize external knowledge from general KGs or static domain KGs to prompt LLM for enhanced domain-specific reasoning, WTS proposes an innovative "LLM$\circlearrowright$KG" paradigm, which achieves bidirectional enhancement between specialized LLM and domain knowledge graph (DKG). The proposed paradigm encompasses two closely coupled components: the DKG-Augmented LLM and the LLM-Assisted DKG Evolution. The former retrieves question-relevant domain knowledge from DKG and uses it to prompt LLM to enhance the reasoning capability for domain-specific tasks; the latter leverages LLM to generate new domain knowledge from processed tasks and use it to evolve DKG. WTS closes the loop between DKG-Augmented LLM and LLM-Assisted DKG Evolution, enabling continuous improvement in the domain specialization as it progressively answers and learns from domain-specific questions. We validate the performance of WTS on 6 datasets spanning 5 domains. The experimental results show that WTS surpasses the previous SOTA in 4 specialized domains and achieves a maximum performance improvement of 11.3%. △ Less

Submitted 28 November, 2024; originally announced November 2024.

Comments: Accepted by KDD 2025

LoFLAT: Local Feature Matching using Focused Linear Attention Transformer

Authors: Naijian Cao, Renjie He, Yuchao Dai, Mingyi He

Abstract: Local feature matching is an essential technique in image matching and plays a critical role in a wide range of vision-based applications. However, existing Transformer-based detector-free local feature matching methods encounter challenges due to the quadratic computational complexity of attention mechanisms, especially at high resolutions. However, while existing Transformer-based detector-free… ▽ More Local feature matching is an essential technique in image matching and plays a critical role in a wide range of vision-based applications. However, existing Transformer-based detector-free local feature matching methods encounter challenges due to the quadratic computational complexity of attention mechanisms, especially at high resolutions. However, while existing Transformer-based detector-free local feature matching methods have reduced computational costs using linear attention mechanisms, they still struggle to capture detailed local interactions, which affects the accuracy and robustness of precise local correspondences. In order to enhance representations of attention mechanisms while preserving low computational complexity, we propose the LoFLAT, a novel Local Feature matching using Focused Linear Attention Transformer in this paper. Our LoFLAT consists of three main modules: the Feature Extraction Module, the Feature Transformer Module, and the Matching Module. Specifically, the Feature Extraction Module firstly uses ResNet and a Feature Pyramid Network to extract hierarchical features. The Feature Transformer Module further employs the Focused Linear Attention to refine attention distribution with a focused mapping function and to enhance feature diversity with a depth-wise convolution. Finally, the Matching Module predicts accurate and robust matches through a coarse-to-fine strategy. Extensive experimental evaluations demonstrate that the proposed LoFLAT outperforms the LoFTR method in terms of both efficiency and accuracy. △ Less

Submitted 30 October, 2024; originally announced October 2024.

BestMan: A Modular Mobile Manipulator Platform for Embodied AI with Unified Simulation-Hardware APIs

Authors: Kui Yang, Nieqing Cao, Yan Ding, Chao Chen

Abstract: Embodied Artificial Intelligence (Embodied AI) emphasizes agents' ability to perceive, understand, and act in physical environments. Simulation platforms play a crucial role in advancing this field by enabling the validation and optimization of algorithms. However, existing platforms face challenges such as multilevel technical integration complexity, insufficient modularity, interface heterogenei… ▽ More Embodied Artificial Intelligence (Embodied AI) emphasizes agents' ability to perceive, understand, and act in physical environments. Simulation platforms play a crucial role in advancing this field by enabling the validation and optimization of algorithms. However, existing platforms face challenges such as multilevel technical integration complexity, insufficient modularity, interface heterogeneity, and adaptation to diverse hardware. We present BestMan, a simulation platform based on PyBullet, designed to address these issues. BestMan introduces an integrated multilevel skill chain for seamless coordination across perception, planning, and control; a highly modular architecture for flexible algorithm integration; unified interfaces for smooth simulation-to-reality transfer; and a hardware-agnostic approach for adapting to various mobile manipulator configurations. These features collectively simplify development and enhance platform expandability, making BestMan a valuable tool for Embodied AI research. △ Less

Submitted 17 October, 2024; originally announced October 2024.

Simultaneously Approximating All Norms for Massively Parallel Correlation Clustering

Authors: Nairen Cao, Shi Li, Jia Ye

Abstract: We revisit the simultaneous approximation model for the correlation clustering problem introduced by Davies, Moseley, and Newman[DMN24]. The objective is to find a clustering that minimizes given norms of the disagreement vector over all vertices. We present an efficient algorithm that produces a clustering that is simultaneously a $63.3$-approximation for all monotone symmetric norms. This sign… ▽ More We revisit the simultaneous approximation model for the correlation clustering problem introduced by Davies, Moseley, and Newman[DMN24]. The objective is to find a clustering that minimizes given norms of the disagreement vector over all vertices. We present an efficient algorithm that produces a clustering that is simultaneously a $63.3$-approximation for all monotone symmetric norms. This significantly improves upon the previous approximation ratio of $6348$ due to Davies, Moseley, and Newman[DMN24], which works only for $\ell_p$-norms. To achieve this result, we first reduce the problem to approximating all top-$k$ norms simultaneously, using the connection between monotone symmetric norms and top-$k$ norms established by Chakrabarty and Swamy [CS19]. Then we develop a novel procedure that constructs a $12.66$-approximate fractional clustering for all top-$k$ norms. Our $63.3$-approximation ratio is obtained by combining this with the $5$-approximate rounding algorithm by Kalhan, Makarychev, and Zhou[KMZ19]. We then demonstrate that with a loss of $ε$ in the approximation ratio, the algorithm can be adapted to run in nearly linear time and in the MPC (massively parallel computation) model with poly-logarithmic number of rounds. By allowing a further trade-off in the approximation ratio to $(359+ε)$, the number of MPC rounds can be reduced to a constant. △ Less

Submitted 21 October, 2024; v1 submitted 11 October, 2024; originally announced October 2024.

NextLocLLM: Location Semantics Modeling and Coordinate-Based Next Location Prediction with LLMs

Authors: Shuai Liu, Ning Cao, Yile Chen, Yue Jiang, George Rosario Jagadeesh, Gao Cong

Abstract: Next location prediction is a critical task in human mobility analysis.Existing methods typically formulate it as a classification task based on discrete location IDs, which hinders spatial continuity modeling and limits generalization to new cities. In this paper, we propose NextLocLLM, a novel framework that reformulates next-location prediction as coordinate regression and integrates LLMs for b… ▽ More Next location prediction is a critical task in human mobility analysis.Existing methods typically formulate it as a classification task based on discrete location IDs, which hinders spatial continuity modeling and limits generalization to new cities. In this paper, we propose NextLocLLM, a novel framework that reformulates next-location prediction as coordinate regression and integrates LLMs for both location semantics encoding and coordinate-level prediction. To model location functional semantics, it constructs LLM-enhanced POI embeddings by leveraging language understanding capabilities of LLMs to extract functional semantics from textual descriptions of POI categories. These POI embeddings are combined with spatiotemporal trajectory representation and fed into the same LLM, enabling unified semantic and predictive modeling. A lightweight regression head generates coordinate outputs, which are mapped to top-k candidate locations via post-prediction retrieval module, ensuring structured outputs. Experiments across diverse cities show that NextLocLLM outperforms existing baselines in both supervised and zero-shot settings. Code is available at: https://github.com/liuwj2000/NexelocLLM. △ Less

Submitted 28 September, 2025; v1 submitted 11 October, 2024; originally announced October 2024.

Comments: STIntelligence in CIKM 2025

FastUMI: A Scalable and Hardware-Independent Universal Manipulation Interface with Dataset

Authors: Zhaxizhuoma, Kehui Liu, Chuyue Guan, Zhongjie Jia, Ziniu Wu, Xin Liu, Tianyu Wang, Shuai Liang, Pengan Chen, Pingrui Zhang, Haoming Song, Delin Qu, Dong Wang, Zhigang Wang, Nieqing Cao, Yan Ding, Bin Zhao, Xuelong Li

Abstract: Real-world manipulation data involving robotic arms is crucial for developing generalist action policies, yet such data remains scarce since existing data collection methods are hindered by high costs, hardware dependencies, and complex setup requirements. In this work, we introduce FastUMI, a substantial redesign of the Universal Manipulation Interface (UMI) system that addresses these challenges… ▽ More Real-world manipulation data involving robotic arms is crucial for developing generalist action policies, yet such data remains scarce since existing data collection methods are hindered by high costs, hardware dependencies, and complex setup requirements. In this work, we introduce FastUMI, a substantial redesign of the Universal Manipulation Interface (UMI) system that addresses these challenges by enabling rapid deployment, simplifying hardware-software integration, and delivering robust performance in real-world data acquisition. Compared with UMI, FastUMI has several advantages: 1) It adopts a decoupled hardware design and incorporates extensive mechanical modifications, removing dependencies on specialized robotic components while preserving consistent observation perspectives. 2) It also refines the algorithmic pipeline by replacing complex Visual-Inertial Odometry (VIO) implementations with an off-the-shelf tracking module, significantly reducing deployment complexity while maintaining accuracy. 3) FastUMI includes an ecosystem for data collection, verification, and integration with both established and newly developed imitation learning algorithms, accelerating policy learning advancement. Additionally, we have open-sourced a high-quality dataset of over 10,000 real-world demonstration trajectories spanning 22 everyday tasks, forming one of the most diverse UMI-like datasets to date. Experimental results confirm that FastUMI facilitates rapid deployment, reduces operational costs and labor demands, and maintains robust performance across diverse manipulation scenarios, thereby advancing scalable data-driven robotic learning. △ Less

Submitted 1 February, 2025; v1 submitted 28 September, 2024; originally announced September 2024.

AlignBot: Aligning VLM-powered Customized Task Planning with User Reminders Through Fine-Tuning for Household Robots

Authors: Zhaxizhuoma Zhaxizhuoma, Pengan Chen, Ziniu Wu, Jiawei Sun, Dong Wang, Peng Zhou, Nieqing Cao, Yan Ding, Bin Zhao, Xuelong Li

Abstract: This paper presents AlignBot, a novel framework designed to optimize VLM-powered customized task planning for household robots by effectively aligning with user reminders. In domestic settings, aligning task planning with user reminders poses significant challenges due to the limited quantity, diversity, and multimodal nature of the reminders. To address these challenges, AlignBot employs a fine-t… ▽ More This paper presents AlignBot, a novel framework designed to optimize VLM-powered customized task planning for household robots by effectively aligning with user reminders. In domestic settings, aligning task planning with user reminders poses significant challenges due to the limited quantity, diversity, and multimodal nature of the reminders. To address these challenges, AlignBot employs a fine-tuned LLaVA-7B model, functioning as an adapter for GPT-4o. This adapter model internalizes diverse forms of user reminders-such as personalized preferences, corrective guidance, and contextual assistance-into structured instruction-formatted cues that prompt GPT-4o in generating customized task plans. Additionally, AlignBot integrates a dynamic retrieval mechanism that selects task-relevant historical successes as prompts for GPT-4o, further enhancing task planning accuracy. To validate the effectiveness of AlignBot, experiments are conducted in real-world household environments, which are constructed within the laboratory to replicate typical household settings. A multimodal dataset with over 1,500 entries derived from volunteer reminders is used for training and evaluation. The results demonstrate that AlignBot significantly improves customized task planning, outperforming existing LLM- and VLM-powered planners by interpreting and aligning with user reminders, achieving 86.8% success rate compared to the vanilla GPT-4o baseline at 21.6%, reflecting a 65% improvement and over four times greater effectiveness. Supplementary materials are available at: https://yding25.com/AlignBot/ △ Less

Submitted 21 March, 2025; v1 submitted 18 September, 2024; originally announced September 2024.

Towards Graph Prompt Learning: A Survey and Beyond

Authors: Qingqing Long, Yuchen Yan, Peiyan Zhang, Chen Fang, Wentao Cui, Zhiyuan Ning, Meng Xiao, Ning Cao, Xiao Luo, Lingjun Xu, Shiyue Jiang, Zheng Fang, Chong Chen, Xian-Sheng Hua, Yuanchun Zhou

Abstract: Large-scale "pre-train and prompt learning" paradigms have demonstrated remarkable adaptability, enabling broad applications across diverse domains such as question answering, image recognition, and multimodal retrieval. This approach fully leverages the potential of large-scale pre-trained models, reducing downstream data requirements and computational costs while enhancing model applicability ac… ▽ More Large-scale "pre-train and prompt learning" paradigms have demonstrated remarkable adaptability, enabling broad applications across diverse domains such as question answering, image recognition, and multimodal retrieval. This approach fully leverages the potential of large-scale pre-trained models, reducing downstream data requirements and computational costs while enhancing model applicability across various tasks. Graphs, as versatile data structures that capture relationships between entities, play pivotal roles in fields such as social network analysis, recommender systems, and biological graphs. Despite the success of pre-train and prompt learning paradigms in Natural Language Processing (NLP) and Computer Vision (CV), their application in graph domains remains nascent. In graph-structured data, not only do the node and edge features often have disparate distributions, but the topological structures also differ significantly. This diversity in graph data can lead to incompatible patterns or gaps between pre-training and fine-tuning on downstream graphs. We aim to bridge this gap by summarizing methods for alleviating these disparities. This includes exploring prompt design methodologies, comparing related techniques, assessing application scenarios and datasets, and identifying unresolved problems and challenges. This survey categorizes over 100 relevant works in this field, summarizing general design principles and the latest applications, including text-attributed graphs, molecules, proteins, and recommendation systems. Through this extensive review, we provide a foundational understanding of graph prompt learning, aiming to impact not only the graph mining community but also the broader Artificial General Intelligence (AGI) community. △ Less

Submitted 24 September, 2024; v1 submitted 26 August, 2024; originally announced August 2024.

Comments: I have decided to temporarily withdraw this draft as I am in the process of making further revisions to improve its content

Visual Analysis of Multi-outcome Causal Graphs

Authors: Mengjie Fan, Jinlu Yu, Daniel Weiskopf, Nan Cao, Huai-Yu Wang, Liang Zhou

Abstract: We introduce a visual analysis method for multiple causal graphs with different outcome variables, namely, multi-outcome causal graphs. Multi-outcome causal graphs are important in healthcare for understanding multimorbidity and comorbidity. To support the visual analysis, we collaborated with medical experts to devise two comparative visualization techniques at different stages of the analysis pr… ▽ More We introduce a visual analysis method for multiple causal graphs with different outcome variables, namely, multi-outcome causal graphs. Multi-outcome causal graphs are important in healthcare for understanding multimorbidity and comorbidity. To support the visual analysis, we collaborated with medical experts to devise two comparative visualization techniques at different stages of the analysis process. First, a progressive visualization method is proposed for comparing multiple state-of-the-art causal discovery algorithms. The method can handle mixed-type datasets comprising both continuous and categorical variables and assist in the creation of a fine-tuned causal graph of a single outcome. Second, a comparative graph layout technique and specialized visual encodings are devised for the quick comparison of multiple causal graphs. In our visual analysis approach, analysts start by building individual causal graphs for each outcome variable, and then, multi-outcome causal graphs are generated and visualized with our comparative technique for analyzing differences and commonalities of these causal graphs. Evaluation includes quantitative measurements on benchmark datasets, a case study with a medical expert, and expert user studies with real-world health research data. △ Less

Submitted 25 August, 2024; v1 submitted 31 July, 2024; originally announced August 2024.

FreeShell: A Context-Free 4D Printing Technique for Fabricating Complex 3D Triangle Mesh Shells

Authors: Chao Yuan, Nan Cao, Xuejiao Ma, Shengqi Dang

Abstract: Freeform thin-shell surfaces are critical in various fields, but their fabrication is complex and costly. Traditional methods are wasteful and require custom molds, while 3D printing needs extensive support structures and post-processing. Thermoshrinkage actuated 4D printing is an effective method through flat structures fabricating 3D shell. However, existing research faces issues related to prec… ▽ More Freeform thin-shell surfaces are critical in various fields, but their fabrication is complex and costly. Traditional methods are wasteful and require custom molds, while 3D printing needs extensive support structures and post-processing. Thermoshrinkage actuated 4D printing is an effective method through flat structures fabricating 3D shell. However, existing research faces issues related to precise deformation and limited robustness. Addressing these issues is challenging due to three key factors: (1) Difficulty in finding a universal method to control deformation across different materials; (2) Variability in deformation influenced by factors such as printing speed, layer thickness, and heating temperature; (3) Environmental factors affecting the deformation process. To overcome these challenges, we introduce FreeShell, a robust 4D printing technique that uses thermoshrinkage to create precise 3D shells. This method prints triangular tiles connected by shrinkable connectors from a single material. Upon heating, the connectors shrink, moving the tiles to form the desired 3D shape, simplifying fabrication and reducing material and environment dependency. An optimized algorithm for flattening 3D meshes ensures precision in printing. FreeShell demonstrates its effectiveness through various examples and experiments, showcasing accuracy, robustness, and strength, representing advancement in fabricating complex freeform surfaces. △ Less

Submitted 28 July, 2024; originally announced July 2024.

Comments: This paper includes 12 pages and 19 figures

LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits

Authors: Chen-Chia Chang, Yikang Shen, Shaoze Fan, Jing Li, Shun Zhang, Ningyuan Cao, Yiran Chen, Xin Zhang

Abstract: In the realm of electronic and electrical engineering, automation of analog circuit is increasingly vital given the complexity and customized requirements of modern applications. However, existing methods only develop search-based algorithms that require many simulation iterations to design a custom circuit topology, which is usually a time-consuming process. To this end, we introduce LaMAGIC, a p… ▽ More In the realm of electronic and electrical engineering, automation of analog circuit is increasingly vital given the complexity and customized requirements of modern applications. However, existing methods only develop search-based algorithms that require many simulation iterations to design a custom circuit topology, which is usually a time-consuming process. To this end, we introduce LaMAGIC, a pioneering language model-based topology generation model that leverages supervised finetuning for automated analog circuit design. LaMAGIC can efficiently generate an optimized circuit design from the custom specification in a single pass. Our approach involves a meticulous development and analysis of various input and output formulations for circuit. These formulations can ensure canonical representations of circuits and align with the autoregressive nature of LMs to effectively addressing the challenges of representing analog circuits as graphs. The experimental results show that LaMAGIC achieves a success rate of up to 96\% under a strict tolerance of 0.01. We also examine the scalability and adaptability of LaMAGIC, specifically testing its performance on more complex circuits. Our findings reveal the enhanced effectiveness of our adjacency matrix-based circuit formulation with floating-point input, suggesting its suitability for handling intricate circuit designs. This research not only demonstrates the potential of language models in graph generation, but also builds a foundational framework for future explorations in automated analog circuit design. △ Less

Submitted 29 August, 2024; v1 submitted 19 July, 2024; originally announced July 2024.

Comments: Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6253-6262 https://proceedings.mlr.press/v235/chang24c.html

Journal ref: Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6253-6262, 2024

Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures

Authors: Ruiyang Qin, Zheyu Yan, Dewen Zeng, Zhenge Jia, Dancheng Liu, Jianbo Liu, Zhi Zheng, Ningyuan Cao, Kai Ni, Jinjun Xiong, Yiyu Shi

Abstract: Large Language Models (LLMs) deployed on edge devices learn through fine-tuning and updating a certain portion of their parameters. Although such learning methods can be optimized to reduce resource utilization, the overall required resources remain a heavy burden on edge devices. Instead, Retrieval-Augmented Generation (RAG), a resource-efficient LLM learning method, can improve the quality of th… ▽ More Large Language Models (LLMs) deployed on edge devices learn through fine-tuning and updating a certain portion of their parameters. Although such learning methods can be optimized to reduce resource utilization, the overall required resources remain a heavy burden on edge devices. Instead, Retrieval-Augmented Generation (RAG), a resource-efficient LLM learning method, can improve the quality of the LLM-generated content without updating model parameters. However, the RAG-based LLM may involve repetitive searches on the profile data in every user-LLM interaction. This search can lead to significant latency along with the accumulation of user data. Conventional efforts to decrease latency result in restricting the size of saved user data, thus reducing the scalability of RAG as user data continuously grows. It remains an open question: how to free RAG from the constraints of latency and scalability on edge devices? In this paper, we propose a novel framework to accelerate RAG via Computing-in-Memory (CiM) architectures. It accelerates matrix multiplications by performing in-situ computation inside the memory while avoiding the expensive data transfer between the computing unit and memory. Our framework, Robust CiM-backed RAG (RoCR), utilizing a novel contrastive learning-based training method and noise-aware training, can enable RAG to efficiently search profile data with CiM. To the best of our knowledge, this is the first work utilizing CiM to accelerate RAG. △ Less

Submitted 7 May, 2024; originally announced May 2024.

Understanding the Cluster LP for Correlation Clustering

Authors: Nairen Cao, Vincent Cohen-Addad, Euiwoong Lee, Shi Li, Alantha Newman, Lukas Vogl

Abstract: In the classic Correlation Clustering problem introduced by Bansal, Blum, and Chawla (FOCS 2002), the input is a complete graph where edges are labeled either $+$ or $-$, and the goal is to find a partition of the vertices that minimizes the sum of the +edges across parts plus the sum of the -edges within parts. In recent years, Chawla, Makarychev, Schramm and Yaroslavtsev (STOC 2015) gave a 2.06-… ▽ More In the classic Correlation Clustering problem introduced by Bansal, Blum, and Chawla (FOCS 2002), the input is a complete graph where edges are labeled either $+$ or $-$, and the goal is to find a partition of the vertices that minimizes the sum of the +edges across parts plus the sum of the -edges within parts. In recent years, Chawla, Makarychev, Schramm and Yaroslavtsev (STOC 2015) gave a 2.06-approximation by providing a near-optimal rounding of the standard LP, and Cohen-Addad, Lee, Li, and Newman (FOCS 2022, 2023) finally bypassed the integrality gap of 2 for this LP giving a $1.73$-approximation for the problem. In order to create a simple and unified framework for Correlation Clustering similar to those for typical approximate optimization tasks, we propose the cluster LP as a strong linear program for Correlation Clustering. We demonstrate the power of the cluster LP by presenting new rounding algorithms, and providing two analyses, one analytically proving a 1.56-approximation and the other solving a factor-revealing SDP to show a 1.485-approximation. Both proofs introduce principled methods by which to analyze the performance of the algorithm, resulting in a significantly improved approximation guarantee. Finally, we prove an integrality gap of $4/3$ for the cluster LP, showing our 1.485-upper bound cannot be drastically improved. Our gap instance directly inspires an improved NP-hardness of approximation with a ratio $24/23 \approx 1.042$; no explicit hardness ratio was known before. △ Less

Submitted 31 October, 2025; v1 submitted 26 April, 2024; originally announced April 2024.

Comments: The conference version of this paper claimed an approximation ratio of 1.437 whose proof currently has a gap. This version fixes the gap with a slightly worse approximation ratio of 1.485

Learning to Plan and Generate Text with Citations

Authors: Constanza Fierro, Reinald Kim Amplayo, Fantine Huot, Nicola De Cao, Joshua Maynez, Shashi Narayan, Mirella Lapata

Abstract: The increasing demand for the deployment of LLMs in information-seeking scenarios has spurred efforts in creating verifiable systems, which generate responses to queries along with supporting evidence. In this paper, we explore the attribution capabilities of plan-based models which have been recently shown to improve the faithfulness, grounding, and controllability of generated text. We conceptua… ▽ More The increasing demand for the deployment of LLMs in information-seeking scenarios has spurred efforts in creating verifiable systems, which generate responses to queries along with supporting evidence. In this paper, we explore the attribution capabilities of plan-based models which have been recently shown to improve the faithfulness, grounding, and controllability of generated text. We conceptualize plans as a sequence of questions which serve as blueprints of the generated content and its organization. We propose two attribution models that utilize different variants of blueprints, an abstractive model where questions are generated from scratch, and an extractive model where questions are copied from the input. Experiments on long-form question-answering show that planning consistently improves attribution quality. Moreover, the citations generated by blueprint models are more accurate compared to those obtained from LLM-based pipelines lacking a planning component. △ Less

Submitted 23 July, 2024; v1 submitted 4 April, 2024; originally announced April 2024.

Comments: Accepted at ACL 2024